© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119828
    Prev
    Next
    INDEX
    Explanations

    for loops and declarations

    np_acts-logits-general · gemini-2.5-flash-lite

    loop iterator variable declarations in for loops across different programming languages.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     most
    -1.96
     first
    -1.66
     \
    -1.63
    .
    -1.46
     писатель
    -1.36
     немного
    -1.35
    to
    -1.30
     because
    -1.29
     two
    -1.29
     one
    -1.29
    POSITIVE LOGITS
     it
    1.59
     the
    1.40
    dée
    1.38
    restler
    1.37
     persoon
    1.29
    listes
    1.28
    熠
    1.28
     bepaalde
    1.28
    seeable
    1.25
    ścioła
    1.24
    Activations Density 0.007%

    No Known Activations